Arstechnica slams next-gen CPU's.

[GFLPraxis]

http://www.anandtech.com/video/showdoc.aspx?i=2461&p=1


Wow. Not pretty, that. At least the GPU's are vastly better than the original.

BTW...those who told me I was wrong by saying the CPUs on the XBox 360 was the same as the primary core in the PS3, and that they were in order processors (no OOE)...read it and weep, suckers :p


It's definitely worth a read. It explains everything about the next gen consoles processors, even the 1 teraflop vs 2 teraflop thing. If you'll excuse me I've got to go finish it.

[GFLPraxis]

Just like the previous Arstechnica said...

game developer comments (on the record and off the record) have Xenon's performance on branch-intensive game control, AI, and physics code as ranging from mediocre to downright bad. Xenon will be a streaming media monster, but the parts of the game engine that have to do with making the game fun to play (and not just pretty to look at) are probably going to suffer. Even if the PPE's branch prediction is significantly better than I think it is, the relatively meager 1MB L2 cache that the game control, AI, and physics code will have to share with procedural synthesis and other graphics code will ensure that programmers have a hard time getting good performance out of non-graphics parts of the game.

Furthermore, the Xenon may be capable of running six threads at once, but the three types of branch-intensive code listed above are not as amenable to high levels of thread-level parallelization as graphics code. On the other hand, these types of code do benefit greatly from out-of-order execution, which Xenon lacks completely, a decent amount of execution core width, which Xenon also lacks; branch prediction hardware, which Xenon is probably short on; and large caches, which Xenon is definitely short on. The end result is a recipe for a console that provides developers with a wealth of graphics resources but that asks them to do more with less on the non-graphical side of gaming.


At any rate, Playstation 3 fanboys shouldn't get all flush over the idea that the Xenon will struggle on non-graphics code. However bad off Xenon will be in that department, the PS3's Cell will probably be worse. The Cell has only one PPE to the Xenon's three, which means that developers will have to cram all their game control, AI, and physics code into at most two threads that are sharing a very narrow execution core with no instruction window. (Don't bother suggesting that the PS3 can use its SPEs for branch-intensive code, because the SPEs lack branch prediction entirely.) Furthermore, the PS3's L2 is only 512K, which is half the size of the Xenon's L2. So the PS3 doesn't get much help with branches in the cache department. In short, the PS3 may fare a bit worse than the Xenon on non-graphics code, but on the upside it will probably fare a bit better on graphics code because of the seven SPEs



The new article points out:
The one statement that we heard over and over again was that Microsoft was sold on the peak theoretical performance of the Xenon CPU. Ever since the announcement of the Xbox 360 and PS3 hardware, people have been set on comparing Microsoft's figure of 1 trillion floating point operations per second to Sony's figure of 2 trillion floating point operations per second (TFLOPs). Any AnandTech reader should know for a fact that these numbers are meaningless, but just in case you need some reasoning for why, let's look at the facts.



The most ironic bit of it all is that according to developers, if either manufacturer had decided to use an Athlon 64 or a Pentium D in their next-gen console, they would be significantly ahead of the competition in terms of CPU performance.


IMHO they were concentrating on having the highest flop output, the biggest/fanciest numbers, etc., rather than real world performance. Possibly multimedia optimizations as well (like how the PS3 can run 12 HD videos at once while my PC can barely run one).

Could this give the Revolution some catchup room? Imagine if Nintendo just goes with a customized G5 processor instead of going for some exotic in-order PowerPC-based processor like the others. Despite having the cheaper system it could allow them to have a better processor.

OR they could put a cheaper processor in the system and have a better graphics card; since the competition has such sucky processors anyway...

[alex_ant]

This is only a surprise to the people who actually believed all that nonsense about the Cell et al. having a bajillion teraflops and being faster than any chip ever. Surprise surprise, just like the 3DO's M2, the N64's R4300i, and PS2's Emotion Engine before them, which all lured plenty of suckers in with wild claims in their day, these new chips are basically unremarkable gaming chips.

But it doesn't matter. The only thing that matters to the 14 year old kids who will be buying these things is that the Cell/Xenon 1) "have a lot of teraflops" (whatever those are) and 2) have a cool name. The goal is not to make the best games chip, the goal is to try to corner the market on idiots who get carried away by video game hype (it's a huge market).

[michaelrjohnson]

The goal is not to make the best games chip, the goal is to try to corner the market on idiots who get carried away by video game hype (it's a huge market).
Couldn't have said it better myself.

[Eidorian]

OMG TEH ANTI-HYPE!!!111


I'm holding out on Nintendo. I NEED my Nintendo games.

[panphage]

http://www.anandtech.com/video/showdoc.aspx?i=2461&p=1

That link don't go nowhere. Also, is it anandtech doing the slamming or Ars? You got a thread title/url mismatch there. ;)

[jadam]

That link don't go nowhere. Also, is it anandtech doing the slamming or Ars? You got a thread title/url mismatch there. ;)


anandtech pulled the article just recently.

[Fukui]

Well, its pretty obvious that these things are incredibly complex.
I have a feeling that doing this will hurt developers more than help them because they'll need to spend so much time/money on techinal aspects than the creative.

Power is one thing, but isn't it getting ridiculous.
I read that labview article on how labview uses something like dependence rules for concurrent execution, giving multithreading for free basically, but I think in the PS3/XBOX case its more assembly programming/tricks not just designing around multithreading that will cause grey hairs... in any case, debugging will seems like its gonna be a **tch.

[GFLPraxis]

Crap I put Ars instead of An. lol.

[After G]

Wow, that's an awesome read, at least of the quoted part.
For some reason, the link leads to a search page ...

But from what I saw, it doesn't look pretty for next-gen consoles.

I was hard pressed to decide what to get between a Revolution and a PS3. Reading this has made me lean more towards the Revolution, where before the HD capability of PS3 was calling to me. I would have loved HD though; I heard the Revolution was not HD capable ... is this true?

[GFLPraxis]

Don't know yet. Nintendo recently said they're not planning on HD support, but there are huge letter writing campaigns; we'll see.

[GFLPraxis]

PS3 article is pulled for now because Anand is worried about MS tracing his anonymous insider.


Well...that explains that.

[Lacero]

This is only a surprise to the people who actually believed all that nonsense about the Cell et al. having a bajillion teraflops and being faster than any chip ever. Surprise surprise, just like the 3DO's M2, the N64's R4300i, and PS2's Emotion Engine before them, which all lured plenty of suckers in with wild claims in their day, these new chips are basically unremarkable gaming chips.

But it doesn't matter. The only thing that matters to the 14 year old kids who will be buying these things is that the Cell/Xenon 1) "have a lot of teraflops" (whatever those are) and 2) have a cool name. The goal is not to make the best games chip, the goal is to try to corner the market on idiots who get carried away by video game hype (it's a huge market).Seems you are the one with pie all over your face. The new Xenons and Cells are indeed fast, except developers need to rethink how they write their software to take advantage of the hardware.

[raggedjimmi]

At any rate, Playstation 3 fanboys shouldn't get all flush over the idea that the Xenon will struggle on non-graphics code.

wait! forget ninty's next console, thats the biggest revolution in gaming! Playstation fanboys who care for anything other than graphics?! :eek:

seriously im quite glad to not enjoy the company of Microsoft or Sony, all this bickering about which console will be fastest wah-wah.
we're getting to a stage now where you can 2 next-gen games from different consoles next to each other and they will look the same. take me, i dont keep up to date on the latest PS3/Xbox 360 games so if you showed me screenshots i would probably guess they're from the same machine. Nintendo will be the same, only interfacing with the game will be different. so stop crying about CPU and GPU speeds, especially these apparent 'pro' writers.

[acedickson]

What excites me the most about the PS3 is that it will play Blu-Ray discs and support 1080p.

[GFLPraxis]

I've found a mirror of the article.
http://groups-beta.google.com/group/alt.games.video.sony-playstation2/msg/62ff83d96ea78ea9?hl=en